© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14306
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation indicative of programming or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical and technical notation patterns, particularly sequences of digits, mathematical symbols, hexadecimal codes, and structured data formats.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.85
    Tikang
    -0.78
    出版年
    -0.77
    الحياه
    -0.77
     ivelany
    -0.76
     Italijanski
    -0.75
    webElementXpaths
    -0.73
     Meksiku
    -0.73
    adaptiveStyles
    -0.72
     snippetHide
    -0.72
    POSITIVE LOGITS
    </td>
    0.39
     /*#__
    0.37
     Finally
    0.34
    ).
    0.32
    }}}}
    0.31
    ByDefault
    0.31
     */
    0.30
    ))))
    0.30
    );
    0.28
    <eos>
    0.28
    Activations Density 1.434%

    No Known Activations